Triple
T6974667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Telkom Knockout |
E161686
|
entity |
| Predicate | successor |
P78
|
FINISHED |
| Object | MTN 8 |
E161685
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: MTN 8 | Statement: [Telkom Knockout, successor, MTN 8]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MTN 8 Context triple: [Telkom Knockout, successor, MTN 8]
-
A.
MTN 8
chosen
MTN 8 is a South African top-flight football knockout cup competition contested by the eight highest-placed teams from the previous Premier Soccer League season.
-
B.
MTN8
MTN8 is a South African knockout football (soccer) cup competition contested by the top eight teams from the Premier Soccer League.
-
C.
MTN
MTN is the IATA airport code for Martin State Airport, a public airport serving the Baltimore, Maryland area.
-
D.
MTN
MTN is the stock ticker symbol for Vail Resorts, a major operator of ski resorts and mountain recreation properties.
-
E.
Mount Cameroon Race of Hope
Mount Cameroon Race of Hope is a challenging annual mountain marathon in Cameroon that attracts elite and local runners to compete up and down the slopes of Mount Cameroon.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c68854a0d88190bc0bf82263f1afce |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db3bda908190a10a91dc8d043ef1 |
completed | March 27, 2026, 7:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c78839d37c8190a127c01e2aeb71ee |
completed | March 28, 2026, 7:50 a.m. |
Created at: March 27, 2026, 2:30 p.m.